You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

DrugCombPred.ipynb 29KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517518519520521522523524525526527528529530531532533534535536537538539540541542543544545546547548549550551552553554555556557558559560561562563564565566567568569570571572573574575576577578579580581582583584585586587588589590591592593594595596597598599600601602603604605606607608609610611612613614615616617618619620621622623624625626627628629630631632633634635636637638639640641642643644645646647648649650651652653654655656657658659660661662663664665666667668669670671672673674675676677678679680681682683684685686687688689690691692693694695696697698699700701702703704705706707708709710711712713714715716717718719720
  1. {
  2. "cells": [
  3. {
  4. "cell_type": "code",
  5. "execution_count": 2,
  6. "id": "7068baf6",
  7. "metadata": {},
  8. "outputs": [
  9. {
  10. "name": "stdout",
  11. "output_type": "stream",
  12. "text": [
  13. " drug1 drug2\n",
  14. "0 DB00862 DB00966\n",
  15. "1 DB00575 DB00806\n",
  16. "2 DB01242 DB08893\n",
  17. "3 DB01151 DB08883\n",
  18. "4 DB01235 DB01275\n",
  19. "... ... ...\n",
  20. "48509 DB00542 DB01354\n",
  21. "48510 DB00476 DB01239\n",
  22. "48511 DB00621 DB01120\n",
  23. "48512 DB00808 DB01356\n",
  24. "48513 DB00677 DB06287\n",
  25. "\n",
  26. "[48514 rows x 2 columns]\n"
  27. ]
  28. }
  29. ],
  30. "source": [
  31. "import pandas as pd\n",
  32. " \n",
  33. "drug_interactions_df = pd.read_csv('Dataset\\DDI\\SNAP Stanford\\ChCh-Miner_durgbank-chem-chem.tsv', sep='\\t')\n",
  34. " \n",
  35. "# printing data\n",
  36. "print(drug_interactions_df)"
  37. ]
  38. },
  39. {
  40. "cell_type": "code",
  41. "execution_count": 9,
  42. "id": "c6abb956",
  43. "metadata": {},
  44. "outputs": [
  45. {
  46. "data": {
  47. "text/plain": [
  48. "1317"
  49. ]
  50. },
  51. "execution_count": 9,
  52. "metadata": {},
  53. "output_type": "execute_result"
  54. }
  55. ],
  56. "source": [
  57. "# number of drugs in the dataset\n",
  58. "len(drug_interactions_df['drug1'].unique())"
  59. ]
  60. },
  61. {
  62. "cell_type": "code",
  63. "execution_count": 10,
  64. "id": "6cfd6019",
  65. "metadata": {},
  66. "outputs": [],
  67. "source": [
  68. "import xml.etree.ElementTree as ET"
  69. ]
  70. },
  71. {
  72. "cell_type": "code",
  73. "execution_count": 18,
  74. "id": "e6c9e0b2",
  75. "metadata": {},
  76. "outputs": [
  77. {
  78. "name": "stdout",
  79. "output_type": "stream",
  80. "text": [
  81. "<Element '{http://www.drugbank.ca}drugbank' at 0x000002369F945090>\n"
  82. ]
  83. }
  84. ],
  85. "source": [
  86. "tree = ET.parse('Dataset\\DDI\\DrugBank\\\\full_database.xml') \n",
  87. "\n",
  88. "# get the parent tag \n",
  89. "root = tree.getroot() \n",
  90. "\n",
  91. "# print the root (parent) tag along with its memory location \n",
  92. "print(root) \n"
  93. ]
  94. },
  95. {
  96. "cell_type": "code",
  97. "execution_count": 35,
  98. "id": "12ada46d",
  99. "metadata": {},
  100. "outputs": [
  101. {
  102. "data": {
  103. "text/plain": [
  104. "xml.etree.ElementTree.Element"
  105. ]
  106. },
  107. "execution_count": 35,
  108. "metadata": {},
  109. "output_type": "execute_result"
  110. }
  111. ],
  112. "source": [
  113. "type(root)"
  114. ]
  115. },
  116. {
  117. "cell_type": "code",
  118. "execution_count": 3,
  119. "id": "06f2c07d",
  120. "metadata": {},
  121. "outputs": [],
  122. "source": [
  123. "ddi = pd.read_xml('Dataset\\DDI\\DrugBank\\\\full_database.xml')"
  124. ]
  125. },
  126. {
  127. "cell_type": "code",
  128. "execution_count": 4,
  129. "id": "582cc9b6",
  130. "metadata": {},
  131. "outputs": [
  132. {
  133. "data": {
  134. "text/html": [
  135. "<div>\n",
  136. "<style scoped>\n",
  137. " .dataframe tbody tr th:only-of-type {\n",
  138. " vertical-align: middle;\n",
  139. " }\n",
  140. "\n",
  141. " .dataframe tbody tr th {\n",
  142. " vertical-align: top;\n",
  143. " }\n",
  144. "\n",
  145. " .dataframe thead th {\n",
  146. " text-align: right;\n",
  147. " }\n",
  148. "</style>\n",
  149. "<table border=\"1\" class=\"dataframe\">\n",
  150. " <thead>\n",
  151. " <tr style=\"text-align: right;\">\n",
  152. " <th></th>\n",
  153. " <th>type</th>\n",
  154. " <th>created</th>\n",
  155. " <th>updated</th>\n",
  156. " <th>{http://www.drugbank.ca}drugbank-id</th>\n",
  157. " <th>{http://www.drugbank.ca}name</th>\n",
  158. " <th>{http://www.drugbank.ca}description</th>\n",
  159. " <th>{http://www.drugbank.ca}cas-number</th>\n",
  160. " <th>{http://www.drugbank.ca}unii</th>\n",
  161. " <th>{http://www.drugbank.ca}state</th>\n",
  162. " <th>{http://www.drugbank.ca}groups</th>\n",
  163. " <th>...</th>\n",
  164. " <th>{http://www.drugbank.ca}reactions</th>\n",
  165. " <th>{http://www.drugbank.ca}snp-effects</th>\n",
  166. " <th>{http://www.drugbank.ca}snp-adverse-drug-reactions</th>\n",
  167. " <th>{http://www.drugbank.ca}targets</th>\n",
  168. " <th>{http://www.drugbank.ca}enzymes</th>\n",
  169. " <th>{http://www.drugbank.ca}carriers</th>\n",
  170. " <th>{http://www.drugbank.ca}transporters</th>\n",
  171. " <th>{http://www.drugbank.ca}average-mass</th>\n",
  172. " <th>{http://www.drugbank.ca}monoisotopic-mass</th>\n",
  173. " <th>{http://www.drugbank.ca}calculated-properties</th>\n",
  174. " </tr>\n",
  175. " </thead>\n",
  176. " <tbody>\n",
  177. " <tr>\n",
  178. " <th>0</th>\n",
  179. " <td>biotech</td>\n",
  180. " <td>2005-06-13</td>\n",
  181. " <td>2021-10-03</td>\n",
  182. " <td>BIOD00024</td>\n",
  183. " <td>Lepirudin</td>\n",
  184. " <td>Lepirudin is identical to natural hirudin exce...</td>\n",
  185. " <td>138068-37-8</td>\n",
  186. " <td>Y43GF64R34</td>\n",
  187. " <td>liquid</td>\n",
  188. " <td>NaN</td>\n",
  189. " <td>...</td>\n",
  190. " <td>NaN</td>\n",
  191. " <td>NaN</td>\n",
  192. " <td>NaN</td>\n",
  193. " <td>NaN</td>\n",
  194. " <td>NaN</td>\n",
  195. " <td>NaN</td>\n",
  196. " <td>NaN</td>\n",
  197. " <td>NaN</td>\n",
  198. " <td>NaN</td>\n",
  199. " <td>NaN</td>\n",
  200. " </tr>\n",
  201. " <tr>\n",
  202. " <th>1</th>\n",
  203. " <td>biotech</td>\n",
  204. " <td>2005-06-13</td>\n",
  205. " <td>2022-01-02</td>\n",
  206. " <td>BIOD00071</td>\n",
  207. " <td>Cetuximab</td>\n",
  208. " <td>Cetuximab is a recombinant chimeric human/mous...</td>\n",
  209. " <td>205923-56-4</td>\n",
  210. " <td>PQX0D8J21J</td>\n",
  211. " <td>liquid</td>\n",
  212. " <td>NaN</td>\n",
  213. " <td>...</td>\n",
  214. " <td>NaN</td>\n",
  215. " <td>NaN</td>\n",
  216. " <td>NaN</td>\n",
  217. " <td>NaN</td>\n",
  218. " <td>NaN</td>\n",
  219. " <td>NaN</td>\n",
  220. " <td>NaN</td>\n",
  221. " <td>NaN</td>\n",
  222. " <td>NaN</td>\n",
  223. " <td>NaN</td>\n",
  224. " </tr>\n",
  225. " <tr>\n",
  226. " <th>2</th>\n",
  227. " <td>biotech</td>\n",
  228. " <td>2005-06-13</td>\n",
  229. " <td>2022-01-02</td>\n",
  230. " <td>BIOD00001</td>\n",
  231. " <td>Dornase alfa</td>\n",
  232. " <td>Dornase alfa is a biosynthetic form of human d...</td>\n",
  233. " <td>143831-71-4</td>\n",
  234. " <td>953A26OA1Y</td>\n",
  235. " <td>liquid</td>\n",
  236. " <td>NaN</td>\n",
  237. " <td>...</td>\n",
  238. " <td>NaN</td>\n",
  239. " <td>NaN</td>\n",
  240. " <td>NaN</td>\n",
  241. " <td>NaN</td>\n",
  242. " <td>NaN</td>\n",
  243. " <td>NaN</td>\n",
  244. " <td>NaN</td>\n",
  245. " <td>NaN</td>\n",
  246. " <td>NaN</td>\n",
  247. " <td>NaN</td>\n",
  248. " </tr>\n",
  249. " <tr>\n",
  250. " <th>3</th>\n",
  251. " <td>biotech</td>\n",
  252. " <td>2005-06-13</td>\n",
  253. " <td>2021-10-03</td>\n",
  254. " <td>BIOD00084</td>\n",
  255. " <td>Denileukin diftitox</td>\n",
  256. " <td>A recombinant DNA-derived cytotoxic protein co...</td>\n",
  257. " <td>173146-27-5</td>\n",
  258. " <td>25E79B5CTM</td>\n",
  259. " <td>liquid</td>\n",
  260. " <td>NaN</td>\n",
  261. " <td>...</td>\n",
  262. " <td>NaN</td>\n",
  263. " <td>NaN</td>\n",
  264. " <td>NaN</td>\n",
  265. " <td>NaN</td>\n",
  266. " <td>NaN</td>\n",
  267. " <td>NaN</td>\n",
  268. " <td>NaN</td>\n",
  269. " <td>NaN</td>\n",
  270. " <td>NaN</td>\n",
  271. " <td>NaN</td>\n",
  272. " </tr>\n",
  273. " <tr>\n",
  274. " <th>4</th>\n",
  275. " <td>biotech</td>\n",
  276. " <td>2005-06-13</td>\n",
  277. " <td>2022-01-02</td>\n",
  278. " <td>BIOD00052</td>\n",
  279. " <td>Etanercept</td>\n",
  280. " <td>Dimeric fusion protein consisting of the extra...</td>\n",
  281. " <td>185243-69-0</td>\n",
  282. " <td>OP401G7OJC</td>\n",
  283. " <td>liquid</td>\n",
  284. " <td>NaN</td>\n",
  285. " <td>...</td>\n",
  286. " <td>NaN</td>\n",
  287. " <td>NaN</td>\n",
  288. " <td>NaN</td>\n",
  289. " <td>NaN</td>\n",
  290. " <td>NaN</td>\n",
  291. " <td>NaN</td>\n",
  292. " <td>NaN</td>\n",
  293. " <td>NaN</td>\n",
  294. " <td>NaN</td>\n",
  295. " <td>NaN</td>\n",
  296. " </tr>\n",
  297. " <tr>\n",
  298. " <th>...</th>\n",
  299. " <td>...</td>\n",
  300. " <td>...</td>\n",
  301. " <td>...</td>\n",
  302. " <td>...</td>\n",
  303. " <td>...</td>\n",
  304. " <td>...</td>\n",
  305. " <td>...</td>\n",
  306. " <td>...</td>\n",
  307. " <td>...</td>\n",
  308. " <td>...</td>\n",
  309. " <td>...</td>\n",
  310. " <td>...</td>\n",
  311. " <td>...</td>\n",
  312. " <td>...</td>\n",
  313. " <td>...</td>\n",
  314. " <td>...</td>\n",
  315. " <td>...</td>\n",
  316. " <td>...</td>\n",
  317. " <td>...</td>\n",
  318. " <td>...</td>\n",
  319. " <td>...</td>\n",
  320. " </tr>\n",
  321. " <tr>\n",
  322. " <th>14589</th>\n",
  323. " <td>small molecule</td>\n",
  324. " <td>2021-12-02</td>\n",
  325. " <td>2021-12-03</td>\n",
  326. " <td>DB16742</td>\n",
  327. " <td>RP-67580</td>\n",
  328. " <td>None</td>\n",
  329. " <td>135911-02-3</td>\n",
  330. " <td>49U9M41BGY</td>\n",
  331. " <td>None</td>\n",
  332. " <td>NaN</td>\n",
  333. " <td>...</td>\n",
  334. " <td>NaN</td>\n",
  335. " <td>NaN</td>\n",
  336. " <td>NaN</td>\n",
  337. " <td>NaN</td>\n",
  338. " <td>NaN</td>\n",
  339. " <td>NaN</td>\n",
  340. " <td>NaN</td>\n",
  341. " <td>NaN</td>\n",
  342. " <td>NaN</td>\n",
  343. " <td>NaN</td>\n",
  344. " </tr>\n",
  345. " <tr>\n",
  346. " <th>14590</th>\n",
  347. " <td>small molecule</td>\n",
  348. " <td>2021-12-02</td>\n",
  349. " <td>2021-12-03</td>\n",
  350. " <td>DB16743</td>\n",
  351. " <td>Nolpitantium chloride</td>\n",
  352. " <td>None</td>\n",
  353. " <td>153050-21-6</td>\n",
  354. " <td>22O6XI63E0</td>\n",
  355. " <td>None</td>\n",
  356. " <td>NaN</td>\n",
  357. " <td>...</td>\n",
  358. " <td>NaN</td>\n",
  359. " <td>NaN</td>\n",
  360. " <td>NaN</td>\n",
  361. " <td>NaN</td>\n",
  362. " <td>NaN</td>\n",
  363. " <td>NaN</td>\n",
  364. " <td>NaN</td>\n",
  365. " <td>NaN</td>\n",
  366. " <td>NaN</td>\n",
  367. " <td>NaN</td>\n",
  368. " </tr>\n",
  369. " <tr>\n",
  370. " <th>14591</th>\n",
  371. " <td>small molecule</td>\n",
  372. " <td>2021-12-02</td>\n",
  373. " <td>2021-12-03</td>\n",
  374. " <td>DB16744</td>\n",
  375. " <td>CP-96345</td>\n",
  376. " <td>None</td>\n",
  377. " <td>132746-60-2</td>\n",
  378. " <td>W22ILA2I52</td>\n",
  379. " <td>None</td>\n",
  380. " <td>NaN</td>\n",
  381. " <td>...</td>\n",
  382. " <td>NaN</td>\n",
  383. " <td>NaN</td>\n",
  384. " <td>NaN</td>\n",
  385. " <td>NaN</td>\n",
  386. " <td>NaN</td>\n",
  387. " <td>NaN</td>\n",
  388. " <td>NaN</td>\n",
  389. " <td>NaN</td>\n",
  390. " <td>NaN</td>\n",
  391. " <td>NaN</td>\n",
  392. " </tr>\n",
  393. " <tr>\n",
  394. " <th>14592</th>\n",
  395. " <td>small molecule</td>\n",
  396. " <td>2021-12-02</td>\n",
  397. " <td>2021-12-03</td>\n",
  398. " <td>DB16745</td>\n",
  399. " <td>PXT 3003</td>\n",
  400. " <td>PXT 3003 is in phase 3 clinical trials for the...</td>\n",
  401. " <td>1467047-91-1</td>\n",
  402. " <td>None</td>\n",
  403. " <td>None</td>\n",
  404. " <td>NaN</td>\n",
  405. " <td>...</td>\n",
  406. " <td>NaN</td>\n",
  407. " <td>NaN</td>\n",
  408. " <td>NaN</td>\n",
  409. " <td>NaN</td>\n",
  410. " <td>NaN</td>\n",
  411. " <td>NaN</td>\n",
  412. " <td>NaN</td>\n",
  413. " <td>353.466</td>\n",
  414. " <td>353.210327</td>\n",
  415. " <td>NaN</td>\n",
  416. " </tr>\n",
  417. " <tr>\n",
  418. " <th>14593</th>\n",
  419. " <td>biotech</td>\n",
  420. " <td>2021-12-20</td>\n",
  421. " <td>2021-12-24</td>\n",
  422. " <td>DB16746</td>\n",
  423. " <td>Elivaldogene autotemcel</td>\n",
  424. " <td>Adrenoleukodystrophy (ALD) is an X-linked gene...</td>\n",
  425. " <td>None</td>\n",
  426. " <td>KUM75TD6SG</td>\n",
  427. " <td>liquid</td>\n",
  428. " <td>NaN</td>\n",
  429. " <td>...</td>\n",
  430. " <td>NaN</td>\n",
  431. " <td>NaN</td>\n",
  432. " <td>NaN</td>\n",
  433. " <td>NaN</td>\n",
  434. " <td>NaN</td>\n",
  435. " <td>NaN</td>\n",
  436. " <td>NaN</td>\n",
  437. " <td>NaN</td>\n",
  438. " <td>NaN</td>\n",
  439. " <td>NaN</td>\n",
  440. " </tr>\n",
  441. " </tbody>\n",
  442. "</table>\n",
  443. "<p>14594 rows × 58 columns</p>\n",
  444. "</div>"
  445. ],
  446. "text/plain": [
  447. " type created updated \\\n",
  448. "0 biotech 2005-06-13 2021-10-03 \n",
  449. "1 biotech 2005-06-13 2022-01-02 \n",
  450. "2 biotech 2005-06-13 2022-01-02 \n",
  451. "3 biotech 2005-06-13 2021-10-03 \n",
  452. "4 biotech 2005-06-13 2022-01-02 \n",
  453. "... ... ... ... \n",
  454. "14589 small molecule 2021-12-02 2021-12-03 \n",
  455. "14590 small molecule 2021-12-02 2021-12-03 \n",
  456. "14591 small molecule 2021-12-02 2021-12-03 \n",
  457. "14592 small molecule 2021-12-02 2021-12-03 \n",
  458. "14593 biotech 2021-12-20 2021-12-24 \n",
  459. "\n",
  460. " {http://www.drugbank.ca}drugbank-id {http://www.drugbank.ca}name \\\n",
  461. "0 BIOD00024 Lepirudin \n",
  462. "1 BIOD00071 Cetuximab \n",
  463. "2 BIOD00001 Dornase alfa \n",
  464. "3 BIOD00084 Denileukin diftitox \n",
  465. "4 BIOD00052 Etanercept \n",
  466. "... ... ... \n",
  467. "14589 DB16742 RP-67580 \n",
  468. "14590 DB16743 Nolpitantium chloride \n",
  469. "14591 DB16744 CP-96345 \n",
  470. "14592 DB16745 PXT 3003 \n",
  471. "14593 DB16746 Elivaldogene autotemcel \n",
  472. "\n",
  473. " {http://www.drugbank.ca}description \\\n",
  474. "0 Lepirudin is identical to natural hirudin exce... \n",
  475. "1 Cetuximab is a recombinant chimeric human/mous... \n",
  476. "2 Dornase alfa is a biosynthetic form of human d... \n",
  477. "3 A recombinant DNA-derived cytotoxic protein co... \n",
  478. "4 Dimeric fusion protein consisting of the extra... \n",
  479. "... ... \n",
  480. "14589 None \n",
  481. "14590 None \n",
  482. "14591 None \n",
  483. "14592 PXT 3003 is in phase 3 clinical trials for the... \n",
  484. "14593 Adrenoleukodystrophy (ALD) is an X-linked gene... \n",
  485. "\n",
  486. " {http://www.drugbank.ca}cas-number {http://www.drugbank.ca}unii \\\n",
  487. "0 138068-37-8 Y43GF64R34 \n",
  488. "1 205923-56-4 PQX0D8J21J \n",
  489. "2 143831-71-4 953A26OA1Y \n",
  490. "3 173146-27-5 25E79B5CTM \n",
  491. "4 185243-69-0 OP401G7OJC \n",
  492. "... ... ... \n",
  493. "14589 135911-02-3 49U9M41BGY \n",
  494. "14590 153050-21-6 22O6XI63E0 \n",
  495. "14591 132746-60-2 W22ILA2I52 \n",
  496. "14592 1467047-91-1 None \n",
  497. "14593 None KUM75TD6SG \n",
  498. "\n",
  499. " {http://www.drugbank.ca}state {http://www.drugbank.ca}groups ... \\\n",
  500. "0 liquid NaN ... \n",
  501. "1 liquid NaN ... \n",
  502. "2 liquid NaN ... \n",
  503. "3 liquid NaN ... \n",
  504. "4 liquid NaN ... \n",
  505. "... ... ... ... \n",
  506. "14589 None NaN ... \n",
  507. "14590 None NaN ... \n",
  508. "14591 None NaN ... \n",
  509. "14592 None NaN ... \n",
  510. "14593 liquid NaN ... \n",
  511. "\n",
  512. " {http://www.drugbank.ca}reactions {http://www.drugbank.ca}snp-effects \\\n",
  513. "0 NaN NaN \n",
  514. "1 NaN NaN \n",
  515. "2 NaN NaN \n",
  516. "3 NaN NaN \n",
  517. "4 NaN NaN \n",
  518. "... ... ... \n",
  519. "14589 NaN NaN \n",
  520. "14590 NaN NaN \n",
  521. "14591 NaN NaN \n",
  522. "14592 NaN NaN \n",
  523. "14593 NaN NaN \n",
  524. "\n",
  525. " {http://www.drugbank.ca}snp-adverse-drug-reactions \\\n",
  526. "0 NaN \n",
  527. "1 NaN \n",
  528. "2 NaN \n",
  529. "3 NaN \n",
  530. "4 NaN \n",
  531. "... ... \n",
  532. "14589 NaN \n",
  533. "14590 NaN \n",
  534. "14591 NaN \n",
  535. "14592 NaN \n",
  536. "14593 NaN \n",
  537. "\n",
  538. " {http://www.drugbank.ca}targets {http://www.drugbank.ca}enzymes \\\n",
  539. "0 NaN NaN \n",
  540. "1 NaN NaN \n",
  541. "2 NaN NaN \n",
  542. "3 NaN NaN \n",
  543. "4 NaN NaN \n",
  544. "... ... ... \n",
  545. "14589 NaN NaN \n",
  546. "14590 NaN NaN \n",
  547. "14591 NaN NaN \n",
  548. "14592 NaN NaN \n",
  549. "14593 NaN NaN \n",
  550. "\n",
  551. " {http://www.drugbank.ca}carriers {http://www.drugbank.ca}transporters \\\n",
  552. "0 NaN NaN \n",
  553. "1 NaN NaN \n",
  554. "2 NaN NaN \n",
  555. "3 NaN NaN \n",
  556. "4 NaN NaN \n",
  557. "... ... ... \n",
  558. "14589 NaN NaN \n",
  559. "14590 NaN NaN \n",
  560. "14591 NaN NaN \n",
  561. "14592 NaN NaN \n",
  562. "14593 NaN NaN \n",
  563. "\n",
  564. " {http://www.drugbank.ca}average-mass \\\n",
  565. "0 NaN \n",
  566. "1 NaN \n",
  567. "2 NaN \n",
  568. "3 NaN \n",
  569. "4 NaN \n",
  570. "... ... \n",
  571. "14589 NaN \n",
  572. "14590 NaN \n",
  573. "14591 NaN \n",
  574. "14592 353.466 \n",
  575. "14593 NaN \n",
  576. "\n",
  577. " {http://www.drugbank.ca}monoisotopic-mass \\\n",
  578. "0 NaN \n",
  579. "1 NaN \n",
  580. "2 NaN \n",
  581. "3 NaN \n",
  582. "4 NaN \n",
  583. "... ... \n",
  584. "14589 NaN \n",
  585. "14590 NaN \n",
  586. "14591 NaN \n",
  587. "14592 353.210327 \n",
  588. "14593 NaN \n",
  589. "\n",
  590. " {http://www.drugbank.ca}calculated-properties \n",
  591. "0 NaN \n",
  592. "1 NaN \n",
  593. "2 NaN \n",
  594. "3 NaN \n",
  595. "4 NaN \n",
  596. "... ... \n",
  597. "14589 NaN \n",
  598. "14590 NaN \n",
  599. "14591 NaN \n",
  600. "14592 NaN \n",
  601. "14593 NaN \n",
  602. "\n",
  603. "[14594 rows x 58 columns]"
  604. ]
  605. },
  606. "execution_count": 4,
  607. "metadata": {},
  608. "output_type": "execute_result"
  609. }
  610. ],
  611. "source": [
  612. "ddi"
  613. ]
  614. },
  615. {
  616. "cell_type": "code",
  617. "execution_count": 12,
  618. "id": "979b2c1c",
  619. "metadata": {},
  620. "outputs": [
  621. {
  622. "data": {
  623. "text/html": [
  624. "<div>\n",
  625. "<style scoped>\n",
  626. " .dataframe tbody tr th:only-of-type {\n",
  627. " vertical-align: middle;\n",
  628. " }\n",
  629. "\n",
  630. " .dataframe tbody tr th {\n",
  631. " vertical-align: top;\n",
  632. " }\n",
  633. "\n",
  634. " .dataframe thead th {\n",
  635. " text-align: right;\n",
  636. " }\n",
  637. "</style>\n",
  638. "<table border=\"1\" class=\"dataframe\">\n",
  639. " <thead>\n",
  640. " <tr style=\"text-align: right;\">\n",
  641. " <th></th>\n",
  642. " <th>type</th>\n",
  643. " <th>created</th>\n",
  644. " <th>updated</th>\n",
  645. " <th>{http://www.drugbank.ca}drugbank-id</th>\n",
  646. " <th>{http://www.drugbank.ca}name</th>\n",
  647. " <th>{http://www.drugbank.ca}description</th>\n",
  648. " <th>{http://www.drugbank.ca}cas-number</th>\n",
  649. " <th>{http://www.drugbank.ca}unii</th>\n",
  650. " <th>{http://www.drugbank.ca}state</th>\n",
  651. " <th>{http://www.drugbank.ca}groups</th>\n",
  652. " <th>...</th>\n",
  653. " <th>{http://www.drugbank.ca}reactions</th>\n",
  654. " <th>{http://www.drugbank.ca}snp-effects</th>\n",
  655. " <th>{http://www.drugbank.ca}snp-adverse-drug-reactions</th>\n",
  656. " <th>{http://www.drugbank.ca}targets</th>\n",
  657. " <th>{http://www.drugbank.ca}enzymes</th>\n",
  658. " <th>{http://www.drugbank.ca}carriers</th>\n",
  659. " <th>{http://www.drugbank.ca}transporters</th>\n",
  660. " <th>{http://www.drugbank.ca}average-mass</th>\n",
  661. " <th>{http://www.drugbank.ca}monoisotopic-mass</th>\n",
  662. " <th>{http://www.drugbank.ca}calculated-properties</th>\n",
  663. " </tr>\n",
  664. " </thead>\n",
  665. " <tbody>\n",
  666. " </tbody>\n",
  667. "</table>\n",
  668. "<p>0 rows × 58 columns</p>\n",
  669. "</div>"
  670. ],
  671. "text/plain": [
  672. "Empty DataFrame\n",
  673. "Columns: [type, created, updated, {http://www.drugbank.ca}drugbank-id, {http://www.drugbank.ca}name, {http://www.drugbank.ca}description, {http://www.drugbank.ca}cas-number, {http://www.drugbank.ca}unii, {http://www.drugbank.ca}state, {http://www.drugbank.ca}groups, {http://www.drugbank.ca}general-references, {http://www.drugbank.ca}synthesis-reference, {http://www.drugbank.ca}indication, {http://www.drugbank.ca}pharmacodynamics, {http://www.drugbank.ca}mechanism-of-action, {http://www.drugbank.ca}toxicity, {http://www.drugbank.ca}metabolism, {http://www.drugbank.ca}absorption, {http://www.drugbank.ca}half-life, {http://www.drugbank.ca}protein-binding, {http://www.drugbank.ca}route-of-elimination, {http://www.drugbank.ca}volume-of-distribution, {http://www.drugbank.ca}clearance, {http://www.drugbank.ca}classification, {http://www.drugbank.ca}salts, {http://www.drugbank.ca}synonyms, {http://www.drugbank.ca}products, {http://www.drugbank.ca}international-brands, {http://www.drugbank.ca}mixtures, {http://www.drugbank.ca}packagers, {http://www.drugbank.ca}manufacturers, {http://www.drugbank.ca}prices, {http://www.drugbank.ca}categories, {http://www.drugbank.ca}affected-organisms, {http://www.drugbank.ca}dosages, {http://www.drugbank.ca}atc-codes, {http://www.drugbank.ca}ahfs-codes, {http://www.drugbank.ca}pdb-entries, {http://www.drugbank.ca}fda-label, {http://www.drugbank.ca}msds, {http://www.drugbank.ca}patents, {http://www.drugbank.ca}food-interactions, {http://www.drugbank.ca}drug-interactions, {http://www.drugbank.ca}sequences, {http://www.drugbank.ca}experimental-properties, {http://www.drugbank.ca}external-identifiers, {http://www.drugbank.ca}external-links, {http://www.drugbank.ca}pathways, {http://www.drugbank.ca}reactions, {http://www.drugbank.ca}snp-effects, {http://www.drugbank.ca}snp-adverse-drug-reactions, {http://www.drugbank.ca}targets, {http://www.drugbank.ca}enzymes, {http://www.drugbank.ca}carriers, {http://www.drugbank.ca}transporters, {http://www.drugbank.ca}average-mass, {http://www.drugbank.ca}monoisotopic-mass, {http://www.drugbank.ca}calculated-properties]\n",
  674. "Index: []\n",
  675. "\n",
  676. "[0 rows x 58 columns]"
  677. ]
  678. },
  679. "execution_count": 12,
  680. "metadata": {},
  681. "output_type": "execute_result"
  682. }
  683. ],
  684. "source": [
  685. "ddi.loc[ddi['{http://www.drugbank.ca}reactions'].notnull()]"
  686. ]
  687. },
  688. {
  689. "cell_type": "code",
  690. "execution_count": null,
  691. "id": "0692fe4e",
  692. "metadata": {},
  693. "outputs": [],
  694. "source": []
  695. },
  696. {
  697. "cell_type": "code",
  698. "execution_count": null,
  699. "id": "a0612d0e",
  700. "metadata": {},
  701. "outputs": [],
  702. "source": []
  703. }
  704. ],
  705. "metadata": {
  706. "kernelspec": {
  707. "display_name": "Julia 1.8.3",
  708. "language": "julia",
  709. "name": "julia-1.8"
  710. },
  711. "language_info": {
  712. "file_extension": ".jl",
  713. "mimetype": "application/julia",
  714. "name": "julia",
  715. "version": "1.8.3"
  716. }
  717. },
  718. "nbformat": 4,
  719. "nbformat_minor": 5
  720. }